Resource distribution estimation for Data-Intensive workloads: Give me my share & no one gets hurt!

Alireza Khoshkbarforoushha*, Rajiv Ranjan, Peter Strazdins

*Corresponding author for this work

    Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

    2 Citations (Scopus)

    Abstract

    Robust resource share estimation of data-intensive workloads is integral to efficient workload management in a (virtualized) cluster where multiple systems co-exist and share the same infrastructure. However, developing a reliable resource estimator is quite challenging due to (i) heterogeneity of workloads (e.g. stream processing, batch processing, transactional, etc.) in a multi-system shared cluster, (ii) limited (in batch processing) or complete uncertainties (in stream processing) on input data size or arrival rates, and (iii) changing configurations from run to run. To address above challenges, we propose an inclusive framework and related techniques for workload profiling, similar job identification, and resource distribution prediction in a cluster. Our analysis shows that the framework can successfully estimate the whole spectrum of resource usage as probability distribution functions for wide ranges of data-intensive workloads.

    Original languageEnglish
    Title of host publicationAdvances in Service-Oriented and Cloud Computing - Workshops of ESOCC 2015, Revised Selected Papers
    EditorsAntonio Celesti, Philipp Leitner
    PublisherSpringer Verlag
    Pages228-237
    Number of pages10
    ISBN (Print)9783319333120
    DOIs
    Publication statusPublished - 2016
    EventWorkshops on CLIoT, WAS4FI, SeaClouds, CloudWay, IDEA, FedCloudNet 2015 held in conjunction with European Conference on Service-Oriented and Cloud Computing, ESOCC 2015 - Taormina, Italy
    Duration: 15 Sept 201517 Sept 2015

    Publication series

    NameCommunications in Computer and Information Science
    Volume567
    ISSN (Print)1865-0929

    Conference

    ConferenceWorkshops on CLIoT, WAS4FI, SeaClouds, CloudWay, IDEA, FedCloudNet 2015 held in conjunction with European Conference on Service-Oriented and Cloud Computing, ESOCC 2015
    Country/TerritoryItaly
    CityTaormina
    Period15/09/1517/09/15

    Fingerprint

    Dive into the research topics of 'Resource distribution estimation for Data-Intensive workloads: Give me my share & no one gets hurt!'. Together they form a unique fingerprint.

    Cite this